GitHub 近日开源 SpecKit,一个将 AI 编码从“随意提示直接写代码”转为“先定义产品规格再执行”的工具包,已获 119K+ stars。该方法先明确产品需求、澄清缺口、制定技术方案、拆解任务,再让 AI 智能体(支持 Copilot、Claude Code、Codex、Gemini、Cursor、Qwen 等 30+ 工具)按规格文档实现,使规格成为可执行的开发契约,避免因规则不清导致返工。
GitHub recently published this repo SpecKit, an open-source toolkit to fix a big weakness of vibe coding: that AI often starts coding before the product rules are clear.
119K+ stars ⭐️
It turns vibe coding from "ask the AI to build it" into "write the product spec first, then make the AI build from that spec."
Most AI coding today starts with a loose prompt, then jumps straight into code, which often produces working demos but weak requirements, missing edge cases, and messy rework.
Spec Kit pushes the process the other way: first define what the product must do, then clarify gaps, then create a technical plan, then break that plan into tasks, then let the agent implement against those written artifacts.